{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00217588","sets":["581:10784:10787"]},"path":["10787"],"owner":"44499","recid":"217588","title":["SPGC: Integration of Secure Multiparty Computation and Differential Privacy for Gradient Computation on Collaborative Learning "],"pubdate":{"attribute_name":"公開日","attribute_value":"2022-03-15"},"_buckets":{"deposit":"b4e0f7f7-2b1e-4092-a47b-b3457456d2e0"},"_deposit":{"id":"217588","pid":{"type":"depid","value":"217588","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"SPGC: Integration of Secure Multiparty Computation and Differential Privacy for Gradient Computation on Collaborative Learning ","author_link":["563973","563971","563972","563969","563975","563976","563970","563974"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"SPGC: Integration of Secure Multiparty Computation and Differential Privacy for Gradient Computation on Collaborative Learning "},{"subitem_title":"SPGC: Integration of Secure Multiparty Computation and Differential Privacy for Gradient Computation on Collaborative Learning ","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"[特集:若手研究者] collaborative learning, privacy-preserving machine learning, secure multiparty computation, differential privacy","subitem_subject_scheme":"Other"}]},"item_type_id":"2","publish_date":"2022-03-15","item_2_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Information Science and Technology, Osaka University"},{"subitem_text_value":"Graduate School of Information Science and Technology, Osaka University"},{"subitem_text_value":"Graduate School of Information Science and Technology, Osaka University"},{"subitem_text_value":"Graduate School of Information Science and Technology, Osaka University"}]},"item_2_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Information Science and Technology, Osaka University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Information Science and Technology, Osaka University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Information Science and Technology, Osaka University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Information Science and Technology, Osaka University","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/217588/files/IPSJ-JNL6303015.pdf","label":"IPSJ-JNL6303015.pdf"},"date":[{"dateType":"Available","dateValue":"2024-03-15"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-JNL6303015.pdf","filesize":[{"value":"2.7 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"5"},{"tax":["include_tax"],"price":"0","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"8"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"d840bfda-33ce-4bdd-8934-b75b90216f53","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2022 by the Information Processing Society of Japan"}]},"item_2_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Kazuki, Iwahana"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Naoto, Yanai"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Jason, Paul Cruz"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Toru, Fujiwara"}],"nameIdentifiers":[{}]}]},"item_2_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Kazuki, Iwahana","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Naoto, Yanai","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Jason, Paul Cruz","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Toru, Fujiwara","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_2_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00116647","subitem_source_identifier_type":"NCID"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_6501","resourcetype":"journal article"}]},"item_2_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"1882-7764","subitem_source_identifier_type":"ISSN"}]},"item_2_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"Achieving differential privacy and utilizing secure multiparty computation are the two primary approaches used for ensuring privacy in privacy-preserving machine learning. However, the privacy guarantee by existing integration protocols of both approaches for collaborative learning weakens when more participants join the protocols. In this work, we present Secure and Private Gradient Computation (SPGC), a novel collaborative learning framework with a strong privacy guarantee independent of the number of participants while still providing high accuracy. The main idea of SPGC is to create noise for the differential privacy within secure multiparty computation. We also created an implementation of SPGC and used it in experiments to measure its accuracy and training time. The results show that SPGC is more accurate than a naive protocol based on local differential privacy by up to 5.6%. We experimentally show that the training time increases in proportion to the noise generation and then demonstrate that the privacy guarantee is independent of the number of participants as well as the accuracy evaluation.\n------------------------------\nThis is a preprint of an article intended for publication Journal of\nInformation Processing(JIP). This preprint should not be cited. This\narticle should be cited as: Journal of Information Processing Vol.30(2022) (online)\nDOI　http://dx.doi.org/10.2197/ipsjjip.30.209\n------------------------------","subitem_description_type":"Other"}]},"item_2_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Achieving differential privacy and utilizing secure multiparty computation are the two primary approaches used for ensuring privacy in privacy-preserving machine learning. However, the privacy guarantee by existing integration protocols of both approaches for collaborative learning weakens when more participants join the protocols. In this work, we present Secure and Private Gradient Computation (SPGC), a novel collaborative learning framework with a strong privacy guarantee independent of the number of participants while still providing high accuracy. The main idea of SPGC is to create noise for the differential privacy within secure multiparty computation. We also created an implementation of SPGC and used it in experiments to measure its accuracy and training time. The results show that SPGC is more accurate than a naive protocol based on local differential privacy by up to 5.6%. We experimentally show that the training time increases in proportion to the noise generation and then demonstrate that the privacy guarantee is independent of the number of participants as well as the accuracy evaluation.\n------------------------------\nThis is a preprint of an article intended for publication Journal of\nInformation Processing(JIP). This preprint should not be cited. This\narticle should be cited as: Journal of Information Processing Vol.30(2022) (online)\nDOI　http://dx.doi.org/10.2197/ipsjjip.30.209\n------------------------------","subitem_description_type":"Other"}]},"item_2_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌"}],"bibliographicIssueDates":{"bibliographicIssueDate":"2022-03-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"3","bibliographicVolumeNumber":"63"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":217588,"updated":"2025-01-19T15:26:58.395459+00:00","links":{},"created":"2025-01-19T01:18:04.672690+00:00"}